https://chenziyin.cargo.site 陳姿尹 Chen Zi Yin Thu, 05 Feb 2026 05:01:07 +0000 https://chenziyin.cargo.site en https://chenziyin.cargo.site/Latent-Physionotrace Sat, 08 Nov 2025 09:07:17 +0000 陳姿尹 Chen Zi Yin https://chenziyin.cargo.site/Latent-Physionotrace Latent PhysionotraceMechanical Installation, Generative AI Algorithms, Real-Time Animation, Mixed Media Dimensions Variable 2025 潛像描繪儀 機械裝置、機器繪圖、演算法、生成動畫、複合媒材 依場地而定 2025︎&nbsp; Magic Noise: How AI Wanders in the Latent Space, LIN &amp; LIN Gallery ︎ 神奇的雜訊：AI的潛在漫步方式，大未來林舍畫廊 <img width="3975" height="2651" width_o="3975" height_o="2651" data-src="https://freight.cargo.site/t/original/i/f209fc3e7f762d89d030da99b147e98c73ba9028304b7d5cb347bb8f3a1b60c1/srgb-2.jpg" data-mid="240394128" border="0" src="https://freight.cargo.site/w/1000/i/f209fc3e7f762d89d030da99b147e98c73ba9028304b7d5cb347bb8f3a1b60c1/srgb-2.jpg" /> 展場入口處為《潛像描繪儀》畫出的肖像畫 In recent years, the Diffusion Model has become the state of the art (SOTA) in image generation systems. It improves upon earlier “one-step” generative methods by dividing the process into a series of smaller steps. At each step, instead of directly using the model’s computed output, the algorithm randomly selects a nearby result within a certain range. Both experimental data and visual outcomes demonstrate that this modification has brought about a major breakthrough. A similar design principle is also found in large language models. The generated output exists as a vector in latent space—essentially, a coordinate. Randomly selecting another coordinate nearby corresponds to diffusing outward from the original point with a Gaussian probability distribution: the closer a point is, the higher its probability; the farther it is, the lower. This process, known as adding noise, gives the diffusion model its name. In visualizations of models like Stable Diffusion or Midjourney, the process is often represented as “denoising.” However, the true logic that allows AI to approach something resembling creativity lies precisely in the step of adding noise. This is the main reason—and necessity—behind why generative AI produces different results each time. One can imagine this process as AI taking a wandering exploration through latent space, step by step, during its generative journey. This work consists of three installations: a Galton board, an AI image generation algorithm, and a Physionotrace. 近幾年成為影像生成模型SOTA（State of The Art，意指某特定時刻下，某技術、設備或科學領域所達到的最高發展水平或最高級狀態）的Diffusion Model（擴散模型），改良了過去「一步到位」的生成方式，把生成的過程拆成了若干個小step，並且在每一個步驟的運算中，並不直接採用模型運算出來的結果，而是在該結果的「附近」具有隨機性地選擇另一個結果。不論是實驗數據或是肉眼可見的結果，皆表明此改良取得躍升性突破。不僅是影像生成模型，大語言模型中也有類似的設計。 生成出來的結果是一個「潛空間」（Latent Space）的「向量」(可以理解成座標)。在「附近」隨機選擇另一個座標，則為從原本的座標以高斯機率分布「擴散」出去，離原本結果越近機率越高，越遠越小，這個步驟就是所謂的「加雜訊」，也就是「擴散模型」的命名由來。 在stable diffution或是midjourney生成過程的視覺化中，多半是以「降噪」的方式呈現，然而真正讓AI有可能可以往「創造力」討論的演算邏輯，其實「加入雜訊」的這個步驟，這也是生成式AI「為甚麼」且「必須」每次生成結果不一樣的主要原因。可以把這個步驟，想像成AI在一步一步的生成step中，在潛空間裡的漫步與探索。 本作品由三組裝置組成：道爾頓板、AI影像生成演算法、側面描繪儀（Physionotrace）。 <img width="3458" height="2307" width_o="3458" height_o="2307" data-src="https://freight.cargo.site/t/original/i/fcb87cff36c0042b8676f57cef7a718242790d304f07d5ef820d33a082837c7c/srgb-12.jpg" data-mid="240394149" border="0" data-scale="98" src="https://freight.cargo.site/w/1000/i/fcb87cff36c0042b8676f57cef7a718242790d304f07d5ef820d33a082837c7c/srgb-12.jpg" /> <img width="1564" height="2189" width_o="1564" height_o="2189" data-src="https://freight.cargo.site/t/original/i/8197d20a76b494c61545cb2b99e998a8be2e298618ca6f9b0ae7358c2d1efa21/2.jpg" data-mid="240394155" border="0" data-scale="32" src="https://freight.cargo.site/w/1000/i/8197d20a76b494c61545cb2b99e998a8be2e298618ca6f9b0ae7358c2d1efa21/2.jpg" />&nbsp;<img width="1564" height="2189" width_o="1564" height_o="2189" data-src="https://freight.cargo.site/t/original/i/39418dae4b19070986e4e9c652dd80978b9a382caf4d111baa2922ba6a4a7e4c/3.jpg" data-mid="240394156" border="0" data-scale="32" src="https://freight.cargo.site/w/1000/i/39418dae4b19070986e4e9c652dd80978b9a382caf4d111baa2922ba6a4a7e4c/3.jpg" />&nbsp;<img width="1564" height="2189" width_o="1564" height_o="2189" data-src="https://freight.cargo.site/t/original/i/2fbcf2e85e5c08034701bf81d465ff4cf00a670b3683f114172fcc560b929531/4.jpg" data-mid="240394157" border="0" data-scale="32" src="https://freight.cargo.site/w/1000/i/2fbcf2e85e5c08034701bf81d465ff4cf00a670b3683f114172fcc560b929531/4.jpg" />&nbsp; 道爾頓板動力裝置，產生常態分布The work begins with a Galton board, which generates a Gaussian distribution—a type of random distribution originating from real-world physical behavior. This naturally occurring randomness is then used to calculate the Gaussian noise required in the iterative process of an AI image generation model (Diffusion Model). The model follows this data to navigate through latent space, producing half-length profile portraits. 作品首先透過道爾頓板，產生來自真實物理行為的高斯分布（Gaussian Distribution，也就是常態分布）——這是一種源自現實世界的隨機分布。並依此計算出AI影像生成模型（Diffusion Model）在生成的疊代過程中所需的高斯雜訊，引導AI在潛空間（Latent Space）中進行探索，生成半身側面剪影的肖像畫。 <img width="5097" height="3822" width_o="5097" height_o="3822" data-src="https://freight.cargo.site/t/original/i/cf5ff0cd059c6eb157afc7420d57f9212a0069aba7d1993a398b80d936b68358/IMG_7278.JPG" data-mid="240394191" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/cf5ff0cd059c6eb157afc7420d57f9212a0069aba7d1993a398b80d936b68358/IMG_7278.JPG" />&nbsp; <img width="4090" height="3068" width_o="4090" height_o="3068" data-src="https://freight.cargo.site/t/original/i/b511b87ce6243657247f09922a673754ead1f5ad639e4a1c7526672f441bd9da/IMG_7277.JPG" data-mid="240394205" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/b511b87ce6243657247f09922a673754ead1f5ad639e4a1c7526672f441bd9da/IMG_7277.JPG" />生成半身側面剪影的肖像畫 These AI-generated portraits are displayed through a modified Physionotrace, a device originally invented in the late 18th century to trace human silhouettes. In this work, the tracing paper is replaced by an LCD screen stripped of its backlight and polarizing film, while the traditional light source for casting shadows is replaced by the screen’s backlight—a connection to the virtual world. The tracing hand is no longer human but mechanical, using a linkage mechanism to reproduce the AI-generated portraits onto real paper. Each day, the machine draws eight profile silhouettes, moving gradually from chaos to clarity. 這些AI生成的肖像，顯示在一台改造的側面描繪儀上。側面描繪儀原為18世紀末用來描繪人像輪廓的裝置，我們將描圖紙替換成移除了背光板與偏光膜的液晶螢幕，並把傳統用來打出剪影的光源，替換成連結虛擬世界的「螢幕背光」。描圖的手也不再是人手，而是機械手臂，透過連桿機構，把螢幕上的AI肖像描繪到實體紙上。每天這台機器會從雜亂至清晰，依序繪製出8張側面肖像剪影。 <img width="3371" height="2247" width_o="3371" height_o="2247" data-src="https://freight.cargo.site/t/original/i/d697416c7b33c412e58f3638554cd7f38da6cfbd2da062f7468f5e9ab48a8718/srgb-48.jpg" data-mid="240394249" border="0" src="https://freight.cargo.site/w/1000/i/d697416c7b33c412e58f3638554cd7f38da6cfbd2da062f7468f5e9ab48a8718/srgb-48.jpg" /> <img width="3973" height="2649" width_o="3973" height_o="2649" data-src="https://freight.cargo.site/t/original/i/d0b461c1ce753c9ec7ecf77fc3581e80e6c9e8311618679b41415bcf4d7fb91f/srgb-53.jpg" data-mid="240394237" border="0" data-scale="34" src="https://freight.cargo.site/w/1000/i/d0b461c1ce753c9ec7ecf77fc3581e80e6c9e8311618679b41415bcf4d7fb91f/srgb-53.jpg" /> <img width="3752" height="2503" width_o="3752" height_o="2503" data-src="https://freight.cargo.site/t/original/i/fd7a081eb19393254ac2286b0893bad1eaf79c783fba73aa614639b33151f18e/srgb-45.jpg" data-mid="240394248" border="0" data-scale="34" src="https://freight.cargo.site/w/1000/i/fd7a081eb19393254ac2286b0893bad1eaf79c783fba73aa614639b33151f18e/srgb-45.jpg" /> <img width="5536" height="4152" width_o="5536" height_o="4152" data-src="https://freight.cargo.site/t/original/i/da67d30bf2c477c93157023edc0038980fec6ae7d37b68b2c219cf6f1c23022e/IMG_7170.JPG" data-mid="240394229" border="0" data-scale="30" src="https://freight.cargo.site/w/1000/i/da67d30bf2c477c93157023edc0038980fec6ae7d37b68b2c219cf6f1c23022e/IMG_7170.JPG" /> 《潛像描繪儀》繪置側面肖像剪影 By using noise derived from the physical world instead of the computer’s pseudo-random number tables traditionally used in AI, the work establishes a link between the virtual latent space in which AI operates and the tangible physical world humans inhabit. It extends the historical significance of the Physionotrace—a device that once marked the shift from artistic subjectivity to mechanical precision and standardization—into the contemporary revolution of AI-generated imagery, where the act of depiction evolves from representing the visible world to recomposing the virtual one through algorithmic computation. 這件作品試圖用「來自真實世界的雜訊」來取代傳統AI所使用的電腦亂數表，讓AI所運作的虛擬潛空間，能與人類所處的物理世界建立起某種連結。並將18世紀末側面描繪儀代表的歷史意義——見證影像從藝術家的主觀詮釋，邁向「準確化、標準化」的機器觀看方式的影像革命，進一步延伸至AI生成影像從可見世界的描摹到虛擬世界重組演算的再次革命。 <img width="2673" height="1782" width_o="2673" height_o="1782" data-src="https://freight.cargo.site/t/original/i/da1dcaa19de18e2f6b35b3e45d405c89cc92e5d9efda9ae35812413420e7b4d1/srgb-4.jpg" data-mid="240394140" border="0" src="https://freight.cargo.site/w/1000/i/da1dcaa19de18e2f6b35b3e45d405c89cc92e5d9efda9ae35812413420e7b4d1/srgb-4.jpg" /><img width="3933" height="2624" width_o="3933" height_o="2624" data-src="https://freight.cargo.site/t/original/i/4f2a8cb7c01b2cb96856bc0f4f8a0b47c7e49b1e9fb131d3f58354037597abf1/srgb-5.jpg" data-mid="240394259" border="0" data-scale="33" src="https://freight.cargo.site/w/1000/i/4f2a8cb7c01b2cb96856bc0f4f8a0b47c7e49b1e9fb131d3f58354037597abf1/srgb-5.jpg" /> <img width="3900" height="2601" width_o="3900" height_o="2601" data-src="https://freight.cargo.site/t/original/i/aec747633189df2b7ce057b2fc311972b231b9fdd5909a6b35db0e236028ab1a/srgb-7.jpg" data-mid="240394261" border="0" data-scale="33" src="https://freight.cargo.site/w/1000/i/aec747633189df2b7ce057b2fc311972b231b9fdd5909a6b35db0e236028ab1a/srgb-7.jpg" /> <img width="3907" height="2606" width_o="3907" height_o="2606" data-src="https://freight.cargo.site/t/original/i/2311b9ec4f6c3f50ca3e96283551f46a472daed7f98e332b8fa881de2e0a3c38/srgb-6.jpg" data-mid="240394260" border="0" data-scale="33" src="https://freight.cargo.site/w/1000/i/2311b9ec4f6c3f50ca3e96283551f46a472daed7f98e332b8fa881de2e0a3c38/srgb-6.jpg" /> 每天描繪儀會從雜亂至清晰，依序繪製出8張側面肖像剪影。 Operation Steps Galton Board: Generates a Gaussian distribution through physical processes in the real world. Sampling: Samples a specified number of pixels based on this Gaussian distribution. Arrangement: Arranges the sampled pixels into a two-dimensional Gaussian noise map. Transformation: Converts the Gaussian noise map into a latent-space noise map. Generation: Uses this transformed noise map as the added noise required in each step of the diffusion-based image generation process. Hatching: Extracts the contours of the generated portrait and fills them with lines. Physionotrace: Displays the image on the modified Physionotrace screen; a drawing machine traces the image and reproduces it as a physical drawing through a linkage mechanism. 運作步驟 Galton Board： 在物理世界，製造出一組高斯分布 Sampling：以此高斯分布取樣出指定數量的像素 Arrangement：將這些像素排列成二維的高斯噪聲圖 Transformation：將高斯噪聲圖轉換成潛空間的噪聲圖 Generation：將此轉換後的噪聲圖作為生成的step中所需加入的雜訊 Hatching：找出生成的肖像圖的輪廓，並用線條填充 Physionotrace：將影像顯示於側面描繪儀的螢幕上，以繪圖機描繪影像，並透過連桿繪製實體畫作 Special Thanks Lin &amp; Lin Gallery Huang Hao-Min — Installation Design and Production 特別感謝大未來林舍畫廊黃浩旻 裝置設計製作 https://chenziyin.cargo.site/Residual-Noise Mon, 22 Sep 2025 02:49:05 +0000 陳姿尹 Chen Zi Yin https://chenziyin.cargo.site/Residual-Noise Residual Noise Technical pen and silkscreen 38 x 38 cm 2025 噪聲殘影針筆、絹板 38 x 38 cm 2025 ︎ Magic Noise: How AI Wanders in the Latent Space, LIN &amp; LIN Gallery︎ 神奇的雜訊：AI的潛在漫步方式，大未來林舍畫廊 <img width="3765" height="2512" width_o="3765" height_o="2512" data-src="https://freight.cargo.site/t/original/i/cf53a45c365ce1a13b45f4fbd3454d5e88cab1a1515707f98b197f1c08352e41/srgb-33.jpg" data-mid="240394008" border="0" src="https://freight.cargo.site/w/1000/i/cf53a45c365ce1a13b45f4fbd3454d5e88cab1a1515707f98b197f1c08352e41/srgb-33.jpg" /> 《 噪聲殘影 》 樹系列 The work employs a method called “Vibe Coding” to generate prompts for AI, producing programs capable of drawing fractal patterns found in nature—such as branches and snowflakes. Using the same drawing rules, the artist first hand-renders the patterns in black lines on paper, then applies silkscreen printing to overlay the AI-generated version in white lines atop the hand-drawn image. Because the computer’s precise white lines cannot perfectly cover the subtle irregularities of the hand-drawn black ones, traces of disorder remain visible. Through this subtractive process—between manual drawing and silkscreen overlay—the artist “calculates” the imperfections of human gesture, using these residual, chaotic lines to reflect on the abstract meaning of “noise” introduced by generative AI as it wanders through latent space. 本作品透過氛圍編碼（Vibe Coding）給AI提示詞的方式，生成可以繪製大自然中的碎形圖案——樹枝、雪花的程式。接著使用相同的繪製規則，手工以黑色線條畫在圖紙上，再以絹板印刷的方式，將電腦繪製的圖案以白色線條覆蓋在手繪的黑色線條上。電腦精準繪製的白色線條無法覆蓋具有手繪誤差的黑色線條，因而留下隱約可見的雜亂線條。藝術家藉由手繪與絹板的「減法」過程，「計算」人為的不精確性，並透過這些留下的雜亂線條，試圖回應生成式AI在潛空間探索時，加入「雜訊」所蘊含的抽象意義。 <img width="3958" height="2639" width_o="3958" height_o="2639" data-src="https://freight.cargo.site/t/original/i/b658c091c2821823c4b1997c2922ea8a97bea6d36dadb21e82b5985a0517d202/srgb-31.jpg" data-mid="240394007" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/b658c091c2821823c4b1997c2922ea8a97bea6d36dadb21e82b5985a0517d202/srgb-31.jpg" />&nbsp;&nbsp;<img width="1185" height="790" width_o="1185" height_o="790" data-src="https://freight.cargo.site/t/original/i/24c79092e2dea2a75ebac565951e2005ded0ff7ae33779dda3542ed8d4805d22/srgb-40.jpg" data-mid="240394009" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/24c79092e2dea2a75ebac565951e2005ded0ff7ae33779dda3542ed8d4805d22/srgb-40.jpg" /> 《噪聲殘影》樹系列，展場紀錄<img width="3808" height="2540" width_o="3808" height_o="2540" data-src="https://freight.cargo.site/t/original/i/a39dc678aca5b237eaffeee6523f2f702b132503f64f73eb25a5ede46b87bc85/srgb-20.jpg" data-mid="240394004" border="0" src="https://freight.cargo.site/w/1000/i/a39dc678aca5b237eaffeee6523f2f702b132503f64f73eb25a5ede46b87bc85/srgb-20.jpg" /> 《噪聲殘影》雪花系列，展場紀錄 <img width="3742" height="2496" width_o="3742" height_o="2496" data-src="https://freight.cargo.site/t/original/i/3795c50acf013170c3f1eba3f8670b03a95076805d658fb6330e2b241c3ab6de/srgb-22.jpg" data-mid="240394005" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/3795c50acf013170c3f1eba3f8670b03a95076805d658fb6330e2b241c3ab6de/srgb-22.jpg" />&nbsp;&nbsp;<img width="1431" height="954" width_o="1431" height_o="954" data-src="https://freight.cargo.site/t/original/i/a8d8a344884914b539f241eb5663c40a68af3466f4d9c0ab23b4127dc6685551/srgb-29.jpg" data-mid="240394006" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/a8d8a344884914b539f241eb5663c40a68af3466f4d9c0ab23b4127dc6685551/srgb-29.jpg" /> 《噪聲殘影》雪花系列，展場紀錄 Process Details1. Image Generation: Using a large language model with a Vibe Coding approach, the artist generates programs capable of drawing natural fractal geometries such as tree branches and snowflakes. 2. Code Translation: The generated program is then translated into human-readable rules and steps, including precise parameters such as branching angles, length ratios, and positional relationships. 3. Custom Drawing Tools: Special triangular rulers with specific angles and lengths are custom-made. 4. Drawing: Following the translated rules and steps, the artist draws with technical pens of constant line width, minimizing human error as much as possible. 5. Screen Preparation: The AI-generated image is printed via inkjet and exposed to produce a silkscreen stencil. 6. Registration and Printing: The first hand-drawn stroke serves as the reference point for alignment, and the silkscreen image is printed precisely over the drawing. 詳細步驟 1. 生成影像: 透過大型語言模型，使用氛圍編碼的方式，生成可以繪製大自然中的碎形幾何圖案——樹枝、雪花的程式。 2. 轉譯程式碼 : 將該程式轉譯成人類可閱讀的規則與步驟，包含詳細的分支角度、長度比例、位置等等。 3. 訂製繪圖工具 : 訂製特殊角度與長度的三角板。 4. 繪製 : 依照轉譯後規則與步驟，使用粗細不會有變化的針管筆繪製，盡可能地減少誤差。 5. 製版 : 將程式生成的影像透過噴墨、曝光，製作絲絹網板。 6.對位與印刷 : 以繪製的第一個筆劃作為原點對位，並進行絹板印刷。 Special ThanksLin &amp; Lin Gallery Siyat Moses — Silkscreen Production特別感謝大未來林舍畫廊阮原閩 版畫絹印製作 https://chenziyin.cargo.site/Folded-Spacetime Wed, 03 Dec 2025 06:41:47 +0000 陳姿尹 Chen Zi Yin https://chenziyin.cargo.site/Folded-Spacetime Folded Spacetime Custom-designed star projection device Dimension Variable2025 時空摺面自製星空投影裝置尺寸依照空間而定2025 <img width="3862" height="2896" width_o="3862" height_o="2896" data-src="https://freight.cargo.site/t/original/i/888818c211c7d1e043d0ef26d54b881ac19a02140d7d9368e97ecbc7e946335a/_1.jpg" data-mid="241344458" border="0" data-scale="98" src="https://freight.cargo.site/w/1000/i/888818c211c7d1e043d0ef26d54b881ac19a02140d7d9368e97ecbc7e946335a/_1.jpg" /> 《時空摺面》展場紀錄，星空投影在牆面轉角處 <img width="2680" height="3574" width_o="2680" height_o="3574" data-src="https://freight.cargo.site/t/original/i/f5db25c201d7a213ef2dbf980ff3b2b52967b9da58cec52380a1b32cc6cbd846/_4.jpg" data-mid="241344457" border="0" data-scale="35" src="https://freight.cargo.site/w/1000/i/f5db25c201d7a213ef2dbf980ff3b2b52967b9da58cec52380a1b32cc6cbd846/_4.jpg" />&nbsp;&nbsp;<img width="3923" height="2942" width_o="3923" height_o="2942" data-src="https://freight.cargo.site/t/original/i/4a685978ee3d957d6a27ead62267b5106afbdcd24b15f170b828fe77d8bb1fbd/_2.jpg" data-mid="241344459" border="0" data-scale="62" src="https://freight.cargo.site/w/1000/i/4a685978ee3d957d6a27ead62267b5106afbdcd24b15f170b828fe77d8bb1fbd/_2.jpg" /> 《時空摺面》展場紀錄，自製星空投影裝置 Humans perceive depth through the parallax created by the distance between our two eyes. Yet when our gaze reaches astronomical scales, the distance between our eyes becomes negligible. The starry sky thus appears almost entirely flat—countless stars separated by unimaginable distances collapse into adjacent points projected onto the retina. The artist projects a star-field onto wall surfaces set at different angles. As the stars move at a constant speed across the projection, their apparent motion sharply changes when crossing the corner, creating a perceptual distortion. Through this visual fold, the work imagines and responds to humanity’s compressed, sliced understanding of the vast scales of the universe. 人類藉由雙眼之間的距離所產生的的像差而得到立體視覺，當觀看的目標遙遠至宇宙尺度時，雙眼之間的距離顯得微乎其微，幾乎可以忽略不計。於是，人眼對於星空的視覺幾乎是完全平面的，即便這些點點繁星之間，存在著人類窮極一生都無法跨越的距離，在我們眼裡，仍然僅是投影在視網膜上的鄰近小點。 藝術家在把星空影像投影在不同角度的平面上，使等速運轉的天體的在視覺上產生速度變化，試圖以此來想像與回應人類對於浩瀚尺度宇宙的切片、壓縮的認知狀態。 <img width="4032" height="3024" width_o="4032" height_o="3024" data-src="https://freight.cargo.site/t/original/i/63b4a8405d872d6c64a86921be484e9893d6d369677fb98860a11547bb05808f/_3.jpg" data-mid="241344460" border="0" src="https://freight.cargo.site/w/1000/i/63b4a8405d872d6c64a86921be484e9893d6d369677fb98860a11547bb05808f/_3.jpg" /> 《時空摺面》展場紀錄 https://chenziyin.cargo.site/False-Color-Photo-Booth Wed, 17 Sep 2025 08:37:25 +0000 陳姿尹 Chen Zi Yin https://chenziyin.cargo.site/False-Color-Photo-Booth False Color Photo Booth Photo booth、Mixed media Dimension Variable 2025 假色拍貼機 拍貼機、複合媒材 尺寸依空間而定 2025 <img width="3323" height="2493" width_o="3323" height_o="2493" data-src="https://freight.cargo.site/t/original/i/316a4eb386db9eefaa5a1aafab2b1d8bdc652ce98c979cf4389cccbb58b4b954/False-Color-Photo-Booth_1.JPG" data-mid="244702116" border="0" src="https://freight.cargo.site/w/1000/i/316a4eb386db9eefaa5a1aafab2b1d8bdc652ce98c979cf4389cccbb58b4b954/False-Color-Photo-Booth_1.JPG" /> 《假色拍貼機》觀眾繪製完成的假色自拍照 <img width="4625" height="3469" width_o="4625" height_o="3469" data-src="https://freight.cargo.site/t/original/i/550eb38e189e5544b3633154d9ce785447f89578263707f0c5f129ee21f67e3f/3.jpg" data-mid="238314821" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/550eb38e189e5544b3633154d9ce785447f89578263707f0c5f129ee21f67e3f/3.jpg" />&nbsp; &nbsp;<img width="4482" height="3361" width_o="4482" height_o="3361" data-src="https://freight.cargo.site/t/original/i/d5fe27c6378b19a33b46c323338acf3568007838f4c55b34c26cdb20041a46f8/9.jpg" data-mid="238314827" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/d5fe27c6378b19a33b46c323338acf3568007838f4c55b34c26cdb20041a46f8/9.jpg" /> 《假色拍貼機》展場紀錄，右側為拍照區，左側為上色區 Conventional cameras—whether film or digital—are designed to reproduce human vision. Their sensitivity range, RGB filters, and white-balance settings are all aimed at faithfully restoring what our eyes perceive.Astronomical photography, however, has a different goal: to record as much specific information as possible, including light from wavelengths invisible to the human eye. Many of the dazzling images of celestial objects that we admire are in fact composites of such invisible light, later assigned “false colors” to reveal hidden details. This installation invites you to create your own false-color self-portrait. Step into the photo booth and receive a “photograph” represented as a matrix of numbers. With the colored crayons provided, match color intensity to the numerical values and fill in the grid. The result is a one-of-a-kind, hand-crafted false-color selfie. 一般照相機不論是底片相機或是數位相機，感光範圍、RGB濾鏡、白平衡等等的設計目標都是為了再現、還原人眼視覺，然而對於天文攝影來說，目標則是可以記錄下更多、更特定的資訊，這些資訊中包含了很多人眼看不見的波長的光。而我們看到的燦爛的天體照片，其實很多都是由這些不可見光，再套上假色所組合而成。 讓我們試著自己畫一張假色自拍照吧! 觀眾使用拍貼機，將會獲得一張由一堆數字矩陣排列的「照片」，並且可以使用現場提供的各個不同顏色的蠟筆，依據顏色深淺對應到數字大小塗色，獲得一張獨一無二的手工假色自拍照! <img width="2048" height="1366" width_o="2048" height_o="1366" data-src="https://freight.cargo.site/t/original/i/c94f8c5b94294ace3fbf99c39b00da7ad43305e13abe4732b14ab41f23ea17d1/21.-by-.jpg" data-mid="238314818" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/c94f8c5b94294ace3fbf99c39b00da7ad43305e13abe4732b14ab41f23ea17d1/21.-by-.jpg" />&nbsp; &nbsp;<img width="2048" height="1366" width_o="2048" height_o="1366" data-src="https://freight.cargo.site/t/original/i/b6d7f580088c51a62ed796e141ebacfed287aefa5d074739f186be65049bf042/20.-by-4.jpg" data-mid="238314817" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/b6d7f580088c51a62ed796e141ebacfed287aefa5d074739f186be65049bf042/20.-by-4.jpg" /> 《假色拍貼機》 ， 2049媽祖遶月太空站，晶創人文計畫總辦提供 ， 攝影：簡豪江&nbsp; <img width="4848" height="3636" width_o="4848" height_o="3636" data-src="https://freight.cargo.site/t/original/i/872a21ab6539dcd10582645ab66666c373755015ea05ba8b827196be79770e22/5.jpg" data-mid="238314823" border="0" data-scale="99" src="https://freight.cargo.site/w/1000/i/872a21ab6539dcd10582645ab66666c373755015ea05ba8b827196be79770e22/5.jpg" /> 《假色拍貼機》上色提示，數字越小塗越淺的顏色，數字越大塗越深的顏色<img width="3448" height="2587" width_o="3448" height_o="2587" data-src="https://freight.cargo.site/t/original/i/bc6a5778558a920bc3a5674a46ab346c871b981c5bdd9b3a8c257f067ce2fbed/8.jpg" data-mid="238314826" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/bc6a5778558a920bc3a5674a46ab346c871b981c5bdd9b3a8c257f067ce2fbed/8.jpg" />&nbsp; &nbsp;<img width="3865" height="2899" width_o="3865" height_o="2899" data-src="https://freight.cargo.site/t/original/i/47c25278ee63bd16c75416073aa8af17140f00e7d3dc336c6996ddad8b960533/7.jpg" data-mid="238314825" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/47c25278ee63bd16c75416073aa8af17140f00e7d3dc336c6996ddad8b960533/7.jpg" /> 《假色拍貼機》拍攝裝置，點擊螢幕即可開始自拍 <img width="3482" height="2612" width_o="3482" height_o="2612" data-src="https://freight.cargo.site/t/original/i/55412c7f96b45ba7d98e2b5156d94ca3a2b171f8df3b803573b49641b15a6489/10.jpg" data-mid="238314828" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/55412c7f96b45ba7d98e2b5156d94ca3a2b171f8df3b803573b49641b15a6489/10.jpg" />&nbsp; &nbsp;<img width="5187" height="3890" width_o="5187" height_o="3890" data-src="https://freight.cargo.site/t/original/i/d2090c74d9cdc4a8af79f76e7e98a0f7ddab6d74e37336393d6f669898fd5213/4.jpg" data-mid="238314822" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/d2090c74d9cdc4a8af79f76e7e98a0f7ddab6d74e37336393d6f669898fd5213/4.jpg" />《假色拍貼機》觀眾完成的假色自拍照 <img width="2577" height="3436" width_o="2577" height_o="3436" data-src="https://freight.cargo.site/t/original/i/69e2125b248664ac9d1bddc6db412c4ed47d32f3ba57238b83d79bb69bf37aa3/2.jpg" data-mid="238314820" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/69e2125b248664ac9d1bddc6db412c4ed47d32f3ba57238b83d79bb69bf37aa3/2.jpg" />&nbsp; &nbsp;<img width="3802" height="5069" width_o="3802" height_o="5069" data-src="https://freight.cargo.site/t/original/i/fd2f1eebdadd9865747be57a58ae7ce9251bdb68595a9a3c72b3b86c778bc384/1.jpg" data-mid="238314819" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/fd2f1eebdadd9865747be57a58ae7ce9251bdb68595a9a3c72b3b86c778bc384/1.jpg" /> 《假色拍貼機》上色區，選一種顏色，依照數字大小對應顏色深淺上色 裝置設計製作: 黃浩旻 https://chenziyin.cargo.site/Prompt-Dupe-arts Fri, 13 Dec 2024 05:38:57 +0000 陳姿尹 Chen Zi Yin https://chenziyin.cargo.site/Prompt-Dupe-arts Prompt: Dupe artsMixed media、Video118x78cm、6’39” 2024 Prompt: Dupe arts複合媒材、錄像118x78cm、6’39”2024Collaborator : Shanboy CHEN共同創作者：陳宣伯 <img width="6000" height="4000" width_o="6000" height_o="4000" data-src="https://freight.cargo.site/t/original/i/a47665ff7ff87adfcc90d4b14fcd0af228576caf1c42dbe3facebbdbd1199bf9/Dupe-Art___-_1.jpg" data-mid="223299789" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/a47665ff7ff87adfcc90d4b14fcd0af228576caf1c42dbe3facebbdbd1199bf9/Dupe-Art___-_1.jpg" />&nbsp;&nbsp;<img width="6000" height="4000" width_o="6000" height_o="4000" data-src="https://freight.cargo.site/t/original/i/bee812354ecb3906c9c30d14f62b98ee08f4fb86032a8e828f82a7ae23b04215/Dupe-Art___-_4.jpg" data-mid="223299792" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/bee812354ecb3906c9c30d14f62b98ee08f4fb86032a8e828f82a7ae23b04215/Dupe-Art___-_4.jpg" />《Prompt: Dupe arts》，未來媒體藝術節，臺灣當代文化實驗場提供，攝影：三月影像 許博彥The term "Dupe" in Dupe Arts reflects the rise of Dupe Culture that has emerged alongside the booming development of social media and e-commerce platforms in&nbsp;China, with a significant following in the West as well. This culture revolves around the&nbsp;pursuit of lower-priced alternatives that resemble high-end products in quality and&nbsp;style, promoting rational consumption and creativity. It is more than just a trend; it's&nbsp;a lifestyle choice that values resourcefulness over luxury. Unlike counterfeits, dupes&nbsp;do not mimic original trademarks but offer legal alternatives with similar design and&nbsp;functionality, which can even increase consumer desire for the original products by&nbsp;expanding their visibility. Following this philosophy, Dupe Arts is not about copying or mechanical reproduction, like a replica painting, but rather imitation of existing artworks, capturing their&nbsp;essence in a more accessible form. The psychological motivation behind Dupe Arts&nbsp;is both a critique of high art and an aspiration towards it, suggesting potential for&nbsp;broader dissemination. Similarly, image-generating AI operates on a parallel logic by&nbsp;producing visually compelling works at a lower cost through complex imitation and&nbsp;recombination of existing images. In this context, exploring prompts and datasets&nbsp;becomes a new avenue for creativity. For many, the demand for art may not hinge on originality. However, for creators, originality remains a crucial marker of artistic agency. How does the art market assign&nbsp;value? What impact will AI-generated art have as a dupe tool? How should creators&nbsp;respond? We searched "Dupe Arts" on Youtube and saw that Youtubers were teaching a simple and affordable way to draw abstract paintings that looked like those in expensive galleries. We draw according to the steps, and then take photos of the finished works and feed them to the generative AI, which generates a large number of similar abstract paintings. Dupe Arts 中的 Dupe 指的是近幾年隨中國的自媒體、電商平台蓬勃發展所興起的「平替文化」（平價替代品），在歐美亦蔚為風潮。指尋找價格較低但品質和款式跟高價產品相似的替代品的消費現象，並認為尋找的過程可以激發創意和探索。平替文化不僅是省錢的消費現象，更是一種理性消費的生活態度體現。平替品並非仿冒原商品，而是一種相對合法的替代方案，亦可以提升消費者對原商品的嚮往。 承襲於此，Dupe Arts 並非抄襲，也不是如複製畫的機械複製，而更像是對於現成物的「模仿」，透過平價的方式創作出風格接近的作品。Dupe Arts 的心理動機既是對高貴藝術品的反動，同時也是嚮往，更是一種擴散的可能。圖像生成AI 也存在類似邏輯，以低廉的成本對資料集中的現成圖像，進行「複雜的模仿與重組」。為了生成出更滿意的圖像，對於提示詞與資料集的現成圖像的探索，亦成為一種新的創意可能。 從 Dupe Arts 或是圖像生成 AI 來看，對也許為數不少的人來說，他們對藝術的「需求」並不是原創性，然而對身為藝術「供給」者的創作者來說，原創性又是創作者的「能動性」的重要證據。藝術是如何被賦予價值？圖像生成 AI 作為一種平替工具又會產生什麼影響？身為創作者的我們又該如何面對？ 我們在Youtube搜尋「Dupe Arts」，看到Youtuber在教學以簡單又平價的方式，畫出如同昂貴畫廊的抽象繪畫作品。我們照著步驟畫出，再將畫好後的作品翻拍成照片給生成式AI，生成出大量相似的抽象繪畫作品。 <img width="3840" height="2160" width_o="3840" height_o="2160" data-src="https://freight.cargo.site/t/original/i/9908d58fccd48b433afb64c8c1c7f179d977bc118b3ef14c6f0e61c99594bf62/Dupe-Art_Simple-Noodle-Art_4.png" data-mid="223299794" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/9908d58fccd48b433afb64c8c1c7f179d977bc118b3ef14c6f0e61c99594bf62/Dupe-Art_Simple-Noodle-Art_4.png" />&nbsp; <img width="3840" height="2160" width_o="3840" height_o="2160" data-src="https://freight.cargo.site/t/original/i/7d0dcf223c5c966bb15fc7555ab011b9dcd5c388ebe2a8cda0b86a52746c3297/Dupe-Art_Simple-Noodle-Art_5.png" data-mid="223299795" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/7d0dcf223c5c966bb15fc7555ab011b9dcd5c388ebe2a8cda0b86a52746c3297/Dupe-Art_Simple-Noodle-Art_5.png" /><img width="3840" height="2160" width_o="3840" height_o="2160" data-src="https://freight.cargo.site/t/original/i/dcdea0e0b029d7350927c2cea2941b907b2a99ee02a24775500a95af2fe002ec/Dupe-Art_Simple-Noodle-Art_3.png" data-mid="223299793" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/dcdea0e0b029d7350927c2cea2941b907b2a99ee02a24775500a95af2fe002ec/Dupe-Art_Simple-Noodle-Art_3.png" /> &nbsp;<img width="3840" height="2160" width_o="3840" height_o="2160" data-src="https://freight.cargo.site/t/original/i/0cb78043def7613f4e611deccd5f6b055cc8a6eb9447ade9f4a3b5717367081a/Prompt-Dupe-Arts_5_.png" data-mid="223299800" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/0cb78043def7613f4e611deccd5f6b055cc8a6eb9447ade9f4a3b5717367081a/Prompt-Dupe-Arts_5_.png" />《Prompt: Dupe arts》錄像截圖，照著Youtuber的Dupe arts教學畫出抽象作品&nbsp; <img width="3840" height="2160" width_o="3840" height_o="2160" data-src="https://freight.cargo.site/t/original/i/45daf2a45e41c24374cab3e10bfd7584b606642e714b7a0b20f24f5a2b22a353/Prompt-Dupe-Arts_4_.png" data-mid="223299799" border="0" data-scale="99" src="https://freight.cargo.site/w/1000/i/45daf2a45e41c24374cab3e10bfd7584b606642e714b7a0b20f24f5a2b22a353/Prompt-Dupe-Arts_4_.png" />《Prompt: Dupe arts》錄像截圖，用Stable Diffusion生成出大量類似的抽象圖樣<img width="5720" height="3813" width_o="5720" height_o="3813" data-src="https://freight.cargo.site/t/original/i/b72e3dc66c1086c86709435f51ac64d0ef3ba5489138501aa8fea293ce58f096/Dupe-Art___-_2.jpg" data-mid="223299790" border="0" src="https://freight.cargo.site/w/1000/i/b72e3dc66c1086c86709435f51ac64d0ef3ba5489138501aa8fea293ce58f096/Dupe-Art___-_2.jpg" />《Prompt: Dupe arts》，未來媒體藝術節，臺灣當代文化實驗場提供，攝影：三月影像 許博彥 Open Source Software Used: stable-diffusion-webui AGPL-3.0 license ControllNet Apache-2.0 license stable-diffusion-v1-5/stable-diffusion-v1-5 CreativeML Open RAIL-M Youtube Video Source: Dupe for $4,300 Artwork! + Home Decor Updates! RAVEN ELYSE DIY Gaffer: Itami Liang&nbsp; 燈光指導: 梁敦學 https://chenziyin.cargo.site/Observatory-melting-on-the-roof Wed, 06 Nov 2024 06:03:26 +0000 陳姿尹 Chen Zi Yin https://chenziyin.cargo.site/Observatory-melting-on-the-roof Observatory melting on the roof&nbsp;Single-channel video5’11”2024 在屋頂融化的天文台單頻道錄像 5’11”2024 Even if I could have an observatory on the rooftop of my own home, it would feel like I’m only a little closer to astronomy. The vast scale of the distant universe makes my tiny self feel as powerless as a melting observatory. 即便能在自家屋頂擁有天文台，好像也只是靠近天文那麼一點點，遙遠的宇宙尺度之大，渺小的自己就像是融化的天文台般無能為力。 https://chenziyin.cargo.site/Space-Explorer Thu, 05 Feb 2026 05:01:07 +0000 陳姿尹 Chen Zi Yin https://chenziyin.cargo.site/Space-Explorer Space Explorer-Charming Fake Color and Quantified Emotions Taiwan Contemporary Culture Lab (C-LAB), CREATORS Program 2024 宇宙探索號— 迷人的假色與量化的情感臺灣當代文化實驗場 CREATORS創作／研發支持計畫 2024 ︎宇宙探索號 — 迷人的假色與量化的情感 ︎Space Explorer — Charming Fake Color and Quantified Emotions <img width="2384" height="1684" width_o="2384" height_o="1684" data-src="https://freight.cargo.site/t/original/i/a17b068445033e7d95eafbe13e264998ee3c6e25959fb470ac7f6f8b3a1cd1c2/20240417_C-lab-_B_RGB_01.jpg" data-mid="244457612" border="0" src="https://freight.cargo.site/w/1000/i/a17b068445033e7d95eafbe13e264998ee3c6e25959fb470ac7f6f8b3a1cd1c2/20240417_C-lab-_B_RGB_01.jpg" />視覺設計: 周芳伃 The history of humanity’s exploration of the universe extends from naked-eye observations in ancient civilizations to modern scientific instruments, continually pushing beyond the limits of human perception and reshaping our understanding of the world. Information technology has opened up another axis of civilizational development: from the printing press to artificial intelligence, transforming the ways in which knowledge is accumulated and produced. With the emergence of large foundation models, artificial intelligence is no longer merely a tool created by humans, but has gradually become an “other” that explores the universe composed of humanity’s digital traces. This project is structured around two research axes: astronomy and artificial intelligence. The astronomy axis focuses on the visual translation of “false color” and invisible light in astronomical images, and asks whether viewers, when unfamiliar with the techniques and principles behind these images, may come to perceive them as objective truth simply because they appear within scientific or educational contexts. Can subjective images still be regarded as having epistemic value within a scientific framework? This line of inquiry is further extended to everyday visual contexts such as portraits and street scenes, in order to reflect on the relationship between images and reality. The artificial intelligence axis departs from the emotional averaging and filter-bubble effects produced by recommendation systems. Rather than developing a complete system, the project aims to construct a prototype of an interactive system and conduct feasibility studies, using AI to detect viewers’ emotional responses and subtly influence narrative branching, serving as an experimental basis for subsequent artistic creation and research. 人類探索宇宙的歷史，從古文明的裸眼觀測到現代科學儀器，不斷突破感官限制，重塑對世界的認知。資訊科技則開啟另一條文明發展軸線，從印刷術到人工智慧，改變知識的累積與生產方式。隨著⼤型基⽯模型出現，人工智慧不再只是人類的工具，而逐漸成為探索人類數位足跡所構成「宇宙」的他者。 本計畫以「天文」與「人工智慧」為兩條研究軸線。天文部分關注天文影像中「假色」與不可見光的視覺轉譯，思考當觀者並不理解其生成技術與原理時，是否會因影像所處的科學展示場域而自然將其視為客觀真實？主觀影像在科學脈絡中是否仍可能被視為具有知識價值？並嘗試將此影像生產邏輯延伸至日常肖像與街景，反思影像與真實之間的關係。人工智慧部分則從推薦系統造成的情感均值化與同溫層現象出發，嘗試建構互動系統雛型，進行可行性研究，透過 AI偵測觀眾情緒反應並影響敘事分支，作為後續創作與研究的實驗基礎。 <img width="2591" height="1545" width_o="2591" height_o="1545" data-src="https://freight.cargo.site/t/original/i/dbae705c5876f6e0112d111ecd661cb8b0d48d7563c4d1b37923f556b69dd882/.png" data-mid="244457820" border="0" src="https://freight.cargo.site/w/1000/i/dbae705c5876f6e0112d111ecd661cb8b0d48d7563c4d1b37923f556b69dd882/.png" /> Process Sharing During the Project Period 本計畫期間的過程分享 Three-Channel Color Composite Portrait Experiment with Narrowband Filters Experiment in collaboration with Hsieh Hsiang Yu 窄頻濾鏡⼈像三⾊合成實驗 實驗與謝翔宇合作 <img width="4656" height="3522" width_o="4656" height_o="3522" data-src="https://freight.cargo.site/t/original/i/4f115d83334fff251b6c2044d8d9175d3c80dde1506cd7fc3202c5e9cd869c8e/L.jpeg" data-mid="244457968" border="0" data-scale="24" src="https://freight.cargo.site/w/1000/i/4f115d83334fff251b6c2044d8d9175d3c80dde1506cd7fc3202c5e9cd869c8e/L.jpeg" />&nbsp;<img width="4656" height="3522" width_o="4656" height_o="3522" data-src="https://freight.cargo.site/t/original/i/569422571d9385d574cf1bc338cfaeae77c52fe93189033f512bd3350270cdb4/R.jpeg" data-mid="244458076" border="0" data-scale="24" src="https://freight.cargo.site/w/1000/i/569422571d9385d574cf1bc338cfaeae77c52fe93189033f512bd3350270cdb4/R.jpeg" />&nbsp;<img width="4656" height="3522" width_o="4656" height_o="3522" data-src="https://freight.cargo.site/t/original/i/d94de06df021a91eccaedce3678b3f9c2a8d3b7fc2833227b401463ef67666a2/G.jpeg" data-mid="244458098" border="0" data-scale="24" src="https://freight.cargo.site/w/1000/i/d94de06df021a91eccaedce3678b3f9c2a8d3b7fc2833227b401463ef67666a2/G.jpeg" />&nbsp;<img width="4656" height="3522" width_o="4656" height_o="3522" data-src="https://freight.cargo.site/t/original/i/995e3f762d99546ba503bda9f454296f73ab694fd0f642291e43294052c8d9fc/B.jpeg" data-mid="244458099" border="0" data-scale="24" src="https://freight.cargo.site/w/1000/i/995e3f762d99546ba503bda9f454296f73ab694fd0f642291e43294052c8d9fc/B.jpeg" />L &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; R &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; G &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; B<img width="4656" height="3522" width_o="4656" height_o="3522" data-src="https://freight.cargo.site/t/original/i/38ef01c2b3b71fb798ae1e728cea8581beee0b79361b3d4b91208275a6fa68ba/S.jpeg" data-mid="244458102" border="0" data-scale="24" src="https://freight.cargo.site/w/1000/i/38ef01c2b3b71fb798ae1e728cea8581beee0b79361b3d4b91208275a6fa68ba/S.jpeg" />&nbsp;<img width="4656" height="3522" width_o="4656" height_o="3522" data-src="https://freight.cargo.site/t/original/i/4ae109e0e1b0d29a77f8b58646d75ac654ae9139a69072e81a95f89383ee2313/H.jpeg" data-mid="244458103" border="0" data-scale="24" src="https://freight.cargo.site/w/1000/i/4ae109e0e1b0d29a77f8b58646d75ac654ae9139a69072e81a95f89383ee2313/H.jpeg" />&nbsp;<img width="4656" height="3522" width_o="4656" height_o="3522" data-src="https://freight.cargo.site/t/original/i/74f371c46154dc824bcd0438294530498a4b2e7fb10bf4781ad393c48fb69855/O.jpeg" data-mid="244458119" border="0" data-scale="24" src="https://freight.cargo.site/w/1000/i/74f371c46154dc824bcd0438294530498a4b2e7fb10bf4781ad393c48fb69855/O.jpeg" /> S &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; H &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; O<img width="4656" height="3522" width_o="4656" height_o="3522" data-src="https://freight.cargo.site/t/original/i/6d45d25d27e26d1c28d391ee55be557ff6c5585aa879db26e92ce1aa664838c2/HOO.jpg" data-mid="244457965" border="0" data-scale="33" src="https://freight.cargo.site/w/1000/i/6d45d25d27e26d1c28d391ee55be557ff6c5585aa879db26e92ce1aa664838c2/HOO.jpg" />&nbsp;<img width="4656" height="3522" width_o="4656" height_o="3522" data-src="https://freight.cargo.site/t/original/i/fdf41973d25ef57e5f40953f01c1f887b3867a99e563d525ddefcc3452a4d4a2/RGB.jpg" data-mid="244457966" border="0" data-scale="33" src="https://freight.cargo.site/w/1000/i/fdf41973d25ef57e5f40953f01c1f887b3867a99e563d525ddefcc3452a4d4a2/RGB.jpg" />&nbsp;<img width="4656" height="3522" width_o="4656" height_o="3522" data-src="https://freight.cargo.site/t/original/i/e939f5dc190fa147231d19bc3c1abcd089aa6929d29dfa5d476f1b1a43d9b345/SHO.jpg" data-mid="244457967" border="0" data-scale="33" src="https://freight.cargo.site/w/1000/i/e939f5dc190fa147231d19bc3c1abcd089aa6929d29dfa5d476f1b1a43d9b345/SHO.jpg" />HOO &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; RGB &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; SHO We experimented with shooting and compositing images using astronomical camera filters R, G, B, S, H, and O. The narrowband images captured with the S, H, and O filters were re-colored using red, green, and blue channels, a technique commonly known as the “Hubble palette.” However, after observing the composited results, we found that human skin appeared green, while other objects such as clothing or table legs, although also rendered in different colors, did not evoke the same sense of discomfort. When this color shift occurs on the human body, our familiarity with human appearance makes green skin difficult to accept. For astronomers, however, imaging deep-sky objects with narrowband filters and applying false color is a way to highlight structural details of celestial bodies. This approach is not merely for aesthetic purposes, but also allows for clearer differentiation of the spatial distribution of sulfur (S II), hydrogen (Hα), and oxygen (O III), thereby supporting scientific research on astronomical phenomena. 我們嘗試以天⽂相機的R、G、B、S、H、O濾鏡進⾏拍攝及合成。其中S、H、O濾鏡拍攝的窄頻照片，以紅、綠、藍三種顏⾊來重新套⾊，這種套⾊即是俗稱的「哈勃⾊」。然⽽在看到套⾊結果後，發現⼈的⽪膚變成綠⾊，⽽其他的物品像是衣服、桌腳等，即便都呈現不同顏⾊，但並不會感到不舒服。當發⽣在⼈⾝上時，我們對於⼈的長相很熟悉，因⽽無法接受綠⾊的⽪膚。然⽽對於天⽂學家⽽⾔，使⽤濾鏡拍攝深空天體，可以透過套⾊更突出天體的細節，不只是為了好看，也更能分辨出硫（S-II）、氫（H-alpha）、氧（Ｏ-III）的分佈，幫助科學研究天體。 Wanderings on Lulin MountainSpecial thanks to Prof. Wei Hao Wang. 鹿林山遊記 特別感謝王為豪老師 During the course of the project, we visited a number of astronomical institutions and observatories. Among them, Lulin Observatory was a place we had long hoped to visit. With the accompaniment of our project advisor, Prof. Wei Hao Wang, we were able to travel to Lulin Observatory, meet with the director and astronomers, and learn from Wang about the daily maintenance of telescopes and related equipment. We documented the entire visit to Lulin Observatory using a 360-degree camera. As observatories are sites where people on the Earth’s surface observe the universe through telescopes, the unique perspective of 360-degree imaging allows the sky and the ground to be inverted, as if looking back at the observers from the sky. In addition, we invited Prof. Wang to our studio to document how he remotely operates the telescopes located at Lulin Observatory and to demonstrate the process of astronomical photography. Through this, we reflect on how, with the development of technology, the embodied rituals of astronomical research are gradually disappearing. 在計畫執⾏過程中，我們參訪了許多天⽂機構、天⽂台，其中「鹿林天⽂台」是我們很久 之前就⼀直很想去的地⽅。這次透過陪伴顧問王為豪老師，帶我們前往鹿林天⽂台，參訪台長及天⽂研究⼈員，王為豪也分享他平常如何維護望遠鏡等相關設備。我們以360相機紀錄拍攝我們去鹿林天⽂台的整個過程，天⽂台是⼈們在地表透過望遠鏡觀看宇宙的地⽅，⽽透過360獨特的視⾓，可將天空與地⾯反轉，像是從天空回望觀測宇宙的⼈們。除此之外我們也請王為豪來到⼯作室，紀錄他如何遠端操作位於鹿林的望遠鏡，以及⽰範天⽂攝影的照片拍攝過程。以此回應科技的發展，天⽂研究⼈員的⾝體儀式感也隨之消失的過程。 Prototype Study of an AI Interactive System Special thanks to Engineer Shanboy Chen AI互動系統雛型研究 特別感謝陳宣伯工程師 <img width="3827" height="2870" width_o="3827" height_o="2870" data-src="https://freight.cargo.site/t/original/i/f37ffc7779cec3ad94424d92641a09830cba887516ed630b4d291ffc9300772a/_1.jpg" data-mid="244458171" border="0" data-scale="28" src="https://freight.cargo.site/w/1000/i/f37ffc7779cec3ad94424d92641a09830cba887516ed630b4d291ffc9300772a/_1.jpg" />&nbsp; &nbsp;<img width="1440" height="1080" width_o="1440" height_o="1080" data-src="https://freight.cargo.site/t/original/i/ee3e4aa857a172504340871111e958eb0489967876dece531cf8c6162bdb041a/__14.JPG" data-mid="244458163" border="0" data-scale="28" src="https://freight.cargo.site/w/1000/i/ee3e4aa857a172504340871111e958eb0489967876dece531cf8c6162bdb041a/__14.JPG" /> &nbsp; <img width="2864" height="1428" width_o="2864" height_o="1428" data-src="https://freight.cargo.site/t/original/i/e9b6637589db1f1ddf7c58aaa300ccc0f753969fd1e488cd3bd5ead0f0e186c7/9a8d7aa2-9b99-456a-8ec0-01f86349aa3c.jpg" data-mid="244458174" border="0" data-scale="28" src="https://freight.cargo.site/w/1000/i/e9b6637589db1f1ddf7c58aaa300ccc0f753969fd1e488cd3bd5ead0f0e186c7/9a8d7aa2-9b99-456a-8ec0-01f86349aa3c.jpg" /> Open-Source Libraries Used: onnxruntime - Licensed under the MIT License. fastapi - Licensed under the MIT License. screeninfo - Licensed under the MIT License. hsemotion-onnx - Licensed under the Apache-2.0 License. onnx - Licensed under the Apache-2.0 License. opencv-python - Licensed under the Apache-2.0 License. pymongo - Licensed under the Apache-2.0 License. numpy - Licensed under the BSD-3-Clause License. uvicorn - Licensed under the BSD-3-Clause License. See link for details: https://github.com/Shanboy5566/hsemotion-onnx Workshop Documentation工作坊活動紀錄 &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp; &nbsp; &nbsp; &nbsp; https://chenziyin.cargo.site/From-Hsinchu-Science-Park-s-Moon Wed, 25 Sep 2024 05:53:22 +0000 陳姿尹 Chen Zi Yin https://chenziyin.cargo.site/From-Hsinchu-Science-Park-s-Moon From Hsinchu Science Park's MoonDiffuser plates, LEDDimension variable 2024 來自竹科的月光 擴散板、LED燈依場定而定 2024 <img width="3246" height="2160" width_o="3246" height_o="2160" data-src="https://freight.cargo.site/t/original/i/5368a50825fa9ded642f8fb84486dbd6947fdc3f197cfd01dd297bfd9d4b9c83/_.png" data-mid="218651816" border="0" src="https://freight.cargo.site/w/1000/i/5368a50825fa9ded642f8fb84486dbd6947fdc3f197cfd01dd297bfd9d4b9c83/_.png" />《來自竹科的月光》作品展覽紀錄照，美術館5pm打烊後燈亮起。 In the Hsinchu Science Park, after sunset, the streets were immersed in the dim and quiet, and a few vehicles occasionally passed by and broke the silence, driving off from the park. Several neatly arranged glass windows emitted icy white light from the high ground, dwarfing the colossal building so much that even the Moon seemed almost rayless. This was indeed an icy landscape infused with technology. “Clock in, clock out, form the mountains, and protect the country.” In this installation, Simple Noodle Art attempts to integrate the warm tones of the old district with the cold rhythm of the Hsinchu Science Park. Usually lights off at five o’clock in the afternoon, the Hsinchu City Art Gallery shall now take shifts with the Science Park together. In this disorienting time and space, the Science Park’s night view appears in the Gallery, and perhaps, this is the most valuable, yet the least noticeable, landscape of Taiwan. 日落後的新竹科學園區，街道在昏暗與寂靜之中沉浸，偶有一、兩台車聲打破沉默，向園區外駛離。 幾面整齊排列的玻璃窗，從高處透出冷冽的白光，龐大的建築也相形失色，甚至連月光都略顯黯淡，這儼然是一幅充滿科技感的冷調風景。 「上班、下班，護國群山。」 在這件作品中，陽春麵研究舍試圖將美術館所在的舊城區的溫暖氛圍與科學園區的冷調節奏融合。平常在傍晚五點熄燈的美術館，也試著與科學園區一起輪班。科學園區夜晚的景象便在美術館中展現，仿佛時空交錯，這也許是臺灣最重要，卻也最鮮為人知的風景之一。 <img width="3024" height="4032" width_o="3024" height_o="4032" data-src="https://freight.cargo.site/t/original/i/7b99103f6a18d7134d2d3f52653f7574ceda6c14d165f404931b66e3693701ff/__1.jpg" data-mid="218651866" border="0" data-scale="48" src="https://freight.cargo.site/w/1000/i/7b99103f6a18d7134d2d3f52653f7574ceda6c14d165f404931b66e3693701ff/__1.jpg" />&nbsp; <img width="3024" height="4032" width_o="3024" height_o="4032" data-src="https://freight.cargo.site/t/original/i/f3fd8b503cbcef6dfd53c42fd189f6cdb85b0a3d38cf37cfb224949c68d2187a/__2.jpg" data-mid="218651868" border="0" data-scale="48" src="https://freight.cargo.site/w/1000/i/f3fd8b503cbcef6dfd53c42fd189f6cdb85b0a3d38cf37cfb224949c68d2187a/__2.jpg" />《來自竹科的月光》作品製作過程紀錄，將擴散板固定於窗戶上，並用燈照亮，燈具隱藏於展牆後方。<img width="2762" height="1553" width_o="2762" height_o="1553" data-src="https://freight.cargo.site/t/original/i/13495ce851ecd0a4b041587a7c868249d02b2edf2a124055aec50252fb61de85/From-Hsinchu-Science-Park-s-Moon.jpg" data-mid="219579685" border="0" src="https://freight.cargo.site/w/1000/i/13495ce851ecd0a4b041587a7c868249d02b2edf2a124055aec50252fb61de85/From-Hsinchu-Science-Park-s-Moon.jpg" /> https://chenziyin.cargo.site/The-Portrait Tue, 21 Nov 2023 08:01:27 +0000 陳姿尹 Chen Zi Yin https://chenziyin.cargo.site/The-Portrait The PortraitComputer-based installation Dimension variable 2023The Portrait 演算影像裝置依場地而定2023<img width="3000" height="2001" width_o="3000" height_o="2001" data-src="https://freight.cargo.site/t/original/i/5f158f4be8f57d6d0f81bb9c4900566974be5b050521c204ceb22f3357fbed4e/53188183634_f91fbd01f4_o.jpg" data-mid="197471285" border="0" src="https://freight.cargo.site/w/1000/i/5f158f4be8f57d6d0f81bb9c4900566974be5b050521c204ceb22f3357fbed4e/53188183634_f91fbd01f4_o.jpg" /> My Self-portrait，右頻道：The crowd's portrait of me，左頻道：My Self-portrait （圖片提供：忠泰美術館 Jut Art Museum） Two-channel video, The Portrait, is extended from Inter net, which uses noise-like images to express descriptions about the artists via “crowdsourced labeling” and the self-writing through “Google search entries.” The “crowdsourced labeling” and “Google search entries” in Inter net - Labeling me use the technology of text embedding to convert these textual descriptions of the artists into eigenvectors before converting the eigenvectors again into color blocks that are arranged into matrix based on a chronological order. The textual descriptions that are more similar in terms of semantics will produce blocks of more similar colors. These seemingly random noise images in fact reveal the distribution of the artists’ descriptions of “I.” As time progresses, the descriptions of “I” also become fluid and different, and the color distribution changes accordingly. Contrasting the two different types of descriptions of “I” in this work is also an attempt to project the self into these noises that are difficult to identity but highly meaningful. 雙頻道錄像《The Portrait》為《Inter net》系列的延伸作品，兩個頻道分別為《The crowd's portrait of me》與《My Self-portrait》。皆以看似雜訊的影像，分別表現「眾包標註」以及自我書寫的「搜尋紀錄」兩種不同的對我的描述。 我把《Inter net - Labeling me》作品中的「眾包標註」以及「搜尋紀錄」，使用文本嵌入（text embedding）技術，將這些描述我的文本轉換成特徵向量，再將這些特徵向量轉換成一個個色塊，依照時間順序矩陣排列。 語意越接近的文本被轉換成的色塊，顏色會越接近。這些看似隨機的雜訊影像，實際上是對於我的描述的「分佈」（distribution），也就是說隨著時間的推移，對於我的描述隨之流動、變換，影像所呈現出來的色彩分佈也會隨之變化。 我試圖用這種視覺化的方式來對比兩種對我不同的描述的異同。也想把我自己投射在這不易辨識卻富含意義的雜訊之中。 <img width="3000" height="2001" width_o="3000" height_o="2001" data-src="https://freight.cargo.site/t/original/i/b5322b0b7e4610977efb3f6aaf57aaf61ce57e6e1cf61b16fc84894e987c1fcc/53188183674_dedcf05b85_o.jpg" data-mid="197471286" border="0" src="https://freight.cargo.site/w/1000/i/b5322b0b7e4610977efb3f6aaf57aaf61ce57e6e1cf61b16fc84894e987c1fcc/53188183674_dedcf05b85_o.jpg" /> <img width="3000" height="2001" width_o="3000" height_o="2001" data-src="https://freight.cargo.site/t/original/i/de83a13a9115c840d2a5b86e3d2eda639606a3fea9c7d3f757da58a3f9ee90d9/53188318010_9a235485a3_o.jpg" data-mid="197471287" border="0" src="https://freight.cargo.site/w/1000/i/de83a13a9115c840d2a5b86e3d2eda639606a3fea9c7d3f757da58a3f9ee90d9/53188318010_9a235485a3_o.jpg" /> （圖片提供：忠泰美術館 Jut Art Museum） <img width="2160" height="2160" width_o="2160" height_o="2160" data-src="https://freight.cargo.site/t/original/i/82c7891c0ab91a5eadf5e771967e6ffa94ea3ba5992b3b8fac7567409d7c8e5e/drawpic_17.png" data-mid="197471701" border="0" src="https://freight.cargo.site/w/1000/i/82c7891c0ab91a5eadf5e771967e6ffa94ea3ba5992b3b8fac7567409d7c8e5e/drawpic_17.png" />My Self-portrait 影像截圖 https://chenziyin.cargo.site/Exploration-and-Exploitation Tue, 18 Jun 2024 03:22:26 +0000 陳姿尹 Chen Zi Yin https://chenziyin.cargo.site/Exploration-and-Exploitation Exploration and ExploitationAI Interactive Video Dimension Variable 2024 探索與剝削AI互動錄像 依場定而定2024︎Ars Electronica Festival 2024︎林茲電子藝術節 2024<img width="7000" height="4667" width_o="7000" height_o="4667" data-src="https://freight.cargo.site/t/original/i/f2ea4e414ae52c2f1ac412731e38ae8e3779ceecd8d883a94e75270d262d7e9d/240908_52X5213-Enhanced-NR.jpg" data-mid="227162117" border="0" data-scale="100" src="https://freight.cargo.site/w/1000/i/f2ea4e414ae52c2f1ac412731e38ae8e3779ceecd8d883a94e75270d262d7e9d/240908_52X5213-Enhanced-NR.jpg" /><img width="7000" height="4667" width_o="7000" height_o="4667" data-src="https://freight.cargo.site/t/original/i/1b638ba61e4f4cb7a1883b44117503d90d18361f9964f89edfe1a4483025c35d/240908_52X5349-Enhanced-NR.jpg" data-mid="227162139" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/1b638ba61e4f4cb7a1883b44117503d90d18361f9964f89edfe1a4483025c35d/240908_52X5349-Enhanced-NR.jpg" /><img width="7000" height="4667" width_o="7000" height_o="4667" data-src="https://freight.cargo.site/t/original/i/1056b553fbbd3397db008b48a90d4af4b7708bc24ebc490346cd53fb82176212/240907_52X4896.jpg" data-mid="227162156" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/1056b553fbbd3397db008b48a90d4af4b7708bc24ebc490346cd53fb82176212/240907_52X4896.jpg" /> 作品於林茲電子藝術節展出（ 攝影：凹焦影像工作室，圖片：國美館提供 ） Does AI exacerbate social divisions when faced with the dilemma of exploring and exploiting humans? The rise of social media has changed the way and direction of information flow. As AI Recommendation algorithms deliver information in a pandering way, it seemingly increases the opportunity to access more information. However, does it also make it difficult for individuals with different standpoints to receive each other's perspectives, thus leading to an echo chamber? Are content creators in pursuit of reach, affecting the content they create? We have developed an AI interactive video system that utilizes multiple cameras installed at the exhibition venue. The system detects the audience's facial emotions through a AI facial emotion recognition system. Based on the detected emotions, the video branches into different narrative branches. The video content portrays an office worker returning home after work and watching a YouTube video recommended by the algorithm. The YouTube video is from an educational channel introducing the topic of "virtual companions." The audience's emotions—"positive," "neutral," or "negative"—correspond to three different perspectives in the introduction: "tech optimism," "scientific explanation," and "pessimistic warnings," respectively. 當AI面臨探索和剝削人類的兩難境地下，是否加劇了社會分裂？ 社交媒體的崛起改變了信息流動的方式和方向。隨著 AI 推薦算法以迎合的方式傳遞信息，它似乎增加了接觸更多信息的機會。然而，這是否也使得持不同立場的個體難以接收彼此的觀點，從而導致同溫層的形成？內容創作者是否因追求傳播範圍而影響了他們創作的內容？ 我們開發了一個AI互動錄像系統，在展場架設多台攝影機，以AI人臉情緒辨識系統偵測觀眾在觀看時臉部的情緒，跟AI推薦系統演算法一樣，以一種「投其所好」的邏輯，選擇播放的觀點。 影片內容為一名上班族下班回到家，點選推薦演算法推薦的Youtube影片觀看，Youtube影片為一個知識型Youtube頻道以「虛擬伴侶」為題的介紹影片，觀眾的「正面」、「中性」、「負面」分別對應到對於到「科技樂觀主義」、「科普介紹」、「悲觀示警」等三種不同介紹觀點。 <img width="3840" height="2160" width_o="3840" height_o="2160" data-src="https://freight.cargo.site/t/original/i/30773050a5a33dbac73c6ea74b3ce4297d741bccba0ebbb3042f6e43ac2f567a/_.png" data-mid="223767745" border="0" src="https://freight.cargo.site/w/1000/i/30773050a5a33dbac73c6ea74b3ce4297d741bccba0ebbb3042f6e43ac2f567a/_.png" /> The YouTube video collaborated with PanSci to record three different introductory perspectives: positive, neutral, and negative, presented with varying color temperatures and tones. By detecting the facial emotions of viewers while watching, the video adjusts its branching based on their emotional responses. Youtube影片與泛科學合作，錄製了正面、中性、負面三種不同的介紹觀點，&nbsp;以不同的色溫與色調呈現。透過偵測現場觀眾觀看時的人臉情緒，並依據此情緒改變影片的分支。 <img width="7000" height="4667" width_o="7000" height_o="4667" data-src="https://freight.cargo.site/t/original/i/db994fd96434cbd0b96d260f6ebde90b27bf90e46d0730ba883fe6b251bc4a34/240908__52X5518-Enhanced-NR.jpg" data-mid="227162275" border="0" src="https://freight.cargo.site/w/1000/i/db994fd96434cbd0b96d260f6ebde90b27bf90e46d0730ba883fe6b251bc4a34/240908__52X5518-Enhanced-NR.jpg" /><img width="7000" height="4667" width_o="7000" height_o="4667" data-src="https://freight.cargo.site/t/original/i/399d2cda74030ab48655826201a8e146beaa56275e18959ca8fce2c2a675c08e/240904_52X4250-Enhanced-NR.jpg" data-mid="227162289" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/399d2cda74030ab48655826201a8e146beaa56275e18959ca8fce2c2a675c08e/240904_52X4250-Enhanced-NR.jpg" /><img width="7000" height="4667" width_o="7000" height_o="4667" data-src="https://freight.cargo.site/t/original/i/eca9d1045e68974559d5fedc0d28f9d069bc2b144d0cb7c91f280f29ec2cedc5/240908_52X5249-Enhanced-NR.jpg" data-mid="227162291" border="0" data-scale="49" src="https://freight.cargo.site/w/1000/i/eca9d1045e68974559d5fedc0d28f9d069bc2b144d0cb7c91f280f29ec2cedc5/240908_52X5249-Enhanced-NR.jpg" /> 作品於林茲電子藝術節展出（攝影：凹焦影像工作室，圖片：國美館提供） A message board was set up at the exhibition, allowing viewers to respond to the questions posed in the video and express their viewpoints after watching. 展場設置了留言板，觀眾看完影片後可以回應影片中的提問並表達觀點。 <img width="2416" height="938" width_o="2416" height_o="938" data-src="https://freight.cargo.site/t/original/i/f1d08ea7e9409217c1eaabfdfb53fc3321aa2598cd51f8baf28df47d40ca925e/-2024-06-18-3.42.57.png" data-mid="213100095" border="0" data-scale="98" src="https://freight.cargo.site/w/1000/i/f1d08ea7e9409217c1eaabfdfb53fc3321aa2598cd51f8baf28df47d40ca925e/-2024-06-18-3.42.57.png" />Video branching diagram影片分支示意 ︎This project uses the following open-source libraries: onnxruntime - Licensed under the MIT License. fastapi - Licensed under the MIT License. screeninfo - Licensed under the MIT License. hsemotion-onnx - Licensed under the Apache-2.0 License. onnx - Licensed under the Apache-2.0 License. opencv-python - Licensed under the Apache-2.0 License. pymongo - Licensed under the Apache-2.0 License. numpy - Licensed under the BSD-3-Clause License. uvicorn - Licensed under the BSD-3-Clause License. ︎ Github:&nbsp;https://github.com/Shanboy5566/hsemotion-onnx This work was co-produced by National Taiwan Museum of Fine Arts &amp; Ars Electronica in 2024, with support from the Ministry of Culture (Taiwan), R.O.C., under the Technology Art Venues Innovation Project and the Taiwan Content Plan.本作品由文化部「藝文場館科藝創新計畫」和「匯聚臺流文化黑潮計畫」支持，並由國立臺灣美術館與林茲電子藝術節共同製作。 導演：陽春麵研究舍 執行導演：丁啟文 場記：陳姿尹 編劇：丁啟文 編劇助理：謝富丞 、陽春麵研究舍 製作人：陽春麵研究舍 共同製片人：林茲電子藝術節、國立台灣美術館 行政製片人：邱誌勇、賴駿杰、Laura Welzenbach、Emiko Ogawa、Lisa Shchegolkova 協同製片人：泛科學 AI互動系統開發：陳宣伯 、莊向峰 演員：洪德高 、鄭國威 攝影：廖鏡文 燈光：梁敦學 收音：顏英琪 剪輯：陳姿尹、莊向峰 調光：莊向峰 視覺特效：黃詣翔、陳仲威 聲音指導：陳奎瀚 字幕翻譯：戴思博 平面設計：周芳伃 特別感謝：沈伯丞